skills.rest
mims-harvard
mims-harvardOFFICIAL
Explore all skills by this author →
Website𝕏@marinkazitnikGitHub

tooluniverse-clinical-data-integration

Integrates FDA labels, FAERS signals, pharmacogenomics, trials, and literature into drug safety reports.

1.7k|254|Updated Mar 3, 2025
Search Tags:#pharmacogenomics#pharmacovigilance#drug safety#adverse events#faers#disproportionality#fda label
One-click install
npx skills add https://github.com/mims-harvard/ToolUniverse --skill tooluniverse-clinical-data-integration
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tooluniverse-clinical-data-integration
Source: https://github.com/mims-harvard/ToolUniverse/tree/main/plugins/tooluniverse/skills/tooluniverse-clinical-data-integration
Command: npx skills add https://github.com/mims-harvard/ToolUniverse --skill tooluniverse-clinical-data-integration

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Conducting a comprehensive drug safety review requires manually pulling data from FDA labels, FAERS adverse event reports, pharmacogenomic databases, clinical trial registries, and PubMed, then reconciling conflicting evidence across all of them. This Skill orchestrates that entire multi-source workflow into a structured, regulatory-grade safety assessment.

Core Features & Use Cases

  • FDA Label Extraction: Retrieves boxed warnings, contraindications, adverse reactions, and drug interactions from DailyMed and openFDA as the authoritative safety baseline.
  • FAERS Signal Detection: Computes PRR, ROR, and IC disproportionality metrics with 95% confidence intervals, seriousness filtering, and demographic stratification to identify post-market signals.
  • Pharmacogenomic Risk Profiling: Queries CPIC guidelines and FDA PGx biomarkers to identify genotype-specific safety risks and testing recommendations.
  • Use Case: Ask for a full safety review of a drug like warfarin and receive an integrated report comparing labeled risks against real-world FAERS signals, PGx considerations, ongoing safety trials, and published literature, with evidence graded from T1 (regulatory) to T4 (literature-only).

Quick Start

Give me a full safety review for metformin including FDA label warnings, FAERS signals, and pharmacogenomic biomarkers.

Frequently Asked Questions about tooluniverse-clinical-data-integration

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect adverse event signals for a drug using FAERS data?▼

FAERS signal detection uses disproportionality analysis: retrieve top adverse events by report count, then calculate PRR, ROR, and IC metrics for each drug-event pair. A signal is flagged when PRR is at least 2.0, the lower 95% confidence bound exceeds 1.0, and there are at least 3 reports.

How to compare FDA drug label warnings with real-world adverse event reports?▼

Extract boxed warnings, adverse reactions, and interactions from DailyMed and openFDA first, then run FAERS disproportionality analysis on the same drug. Classify each finding as known and labeled, known but under-labeled, or a potential new signal in the integrated report.

What pharmacogenomic data is available for drug safety assessment?▼

The workflow queries CPIC guidelines for gene-drug dosing recommendations and the FDA pharmacogenomic biomarker table for approved PGx labeling. Coverage is limited: only about 30 gene-drug pairs have CPIC guidelines, so absence of a guideline is normal for most drugs.

Does a strong FAERS signal prove a drug causes an adverse event?▼

No. PRR and ROR measure reporting patterns, not causation. Signals can arise from channeling bias, notoriety bias, or protopathic bias, so corroboration from FDA labels, plausible mechanisms, and published epidemiological studies is required before drawing conclusions.

What are the limitations of FAERS-based drug safety analysis?▼

FAERS relies on voluntary spontaneous reports, so under-reporting is common and no denominator exists to calculate incidence rates. Only disproportionality can be measured, and results should always be supplemented with FDA labels, clinical trials, and literature evidence.

Related Skills

Explore More Education & Research Skills→
PKU-YuanGroupPKU-YuanGroup
288

indication-dossier

Generate structured therapeutic indication dossiers through a five-phase research workflow.

Official
Advanced
trevorc-aitrevorc-ai

Clinical Domain Skill

Design and validate psychedelic therapy protocols with structured risk assessment and decision documentation.

Community
Advanced
inflexa-aiinflexa-ai
29

translational-safety

Integrate CTCAE v5 grading, CYP metabolism, and FAERS signal detection for safety assessments.

Official
Advanced
awslabsawslabs
13

pharmacoepidemiology

Design and evaluate pharmacoepidemiologic studies using real-world observational data.

Official
Advanced